climateprediction.net (CPDN) home page
Thread 'Upload server is out of disk space'

Thread 'Upload server is out of disk space'

Message boards : Number crunching : Upload server is out of disk space
Message board moderation

To post messages, you must log in.

Previous · 1 · 2 · 3 · 4 · 5

AuthorMessage
ProfileDave Jackson
Volunteer moderator

Send message
Joined: 15 May 09
Posts: 4541
Credit: 19,039,635
RAC: 18,944
Message 59430 - Posted: 14 Jan 2019, 11:36:02 UTC - in response to Message 59429.  

do you think the server will be back today?


Sarah who set up shifting the data to make space hopes that the transfer will be complete or enough moved to let uploads resume. She has been travelling to a meeting and is hoping to log in remotely to see if things can resume. Afraid I don't think anyone can say more than that but by the end of the day, we should if remote login successful have a bit more information. However when I think of how long it takes my system to back up 250GB worth of data and remember that this is hundreds of Terrabytes.............
ID: 59430 · Report as offensive     Reply Quote
[SG]Felix

Send message
Joined: 4 Oct 15
Posts: 34
Credit: 9,075,151
RAC: 374
Message 59431 - Posted: 14 Jan 2019, 12:21:53 UTC

but you cant compare your system with theis system ;)

i think they can use a big bandwith, at least 10 gbit i think
ID: 59431 · Report as offensive     Reply Quote
ProfileDave Jackson
Volunteer moderator

Send message
Joined: 15 May 09
Posts: 4541
Credit: 19,039,635
RAC: 18,944
Message 59432 - Posted: 14 Jan 2019, 13:52:36 UTC - in response to Message 59431.  

but you cant compare your system with theis system ;)


I was comparing it with a system a lot bigger and faster than my own, (biggest disk on system 20TB) but still small beer compared with what CPDN are dealing with.
ID: 59432 · Report as offensive     Reply Quote
[SG]Felix

Send message
Joined: 4 Oct 15
Posts: 34
Credit: 9,075,151
RAC: 374
Message 59433 - Posted: 14 Jan 2019, 13:58:37 UTC
Last modified: 14 Jan 2019, 14:07:01 UTC

i just uploaded my first zip file, server seems to be back online, upload finished succesfully

Edit:

after ten minutes of uploading files, the connection to the server slows down realy fast. i think other users start to upload their zips too. hopefully the server won't crash
ID: 59433 · Report as offensive     Reply Quote
Les Bayliss
Volunteer moderator

Send message
Joined: 5 Sep 04
Posts: 7629
Credit: 24,240,330
RAC: 0
Message 59434 - Posted: 14 Jan 2019, 14:26:42 UTC

Yes, it's been re-enabled, so go for it.
ID: 59434 · Report as offensive     Reply Quote
[SG]Felix

Send message
Joined: 4 Oct 15
Posts: 34
Credit: 9,075,151
RAC: 374
Message 59435 - Posted: 14 Jan 2019, 14:28:23 UTC

well.... ping over 2 seconds, i think there are many connections incoming right now
ID: 59435 · Report as offensive     Reply Quote
Jean-David Beyer

Send message
Joined: 5 Aug 04
Posts: 1120
Credit: 17,202,915
RAC: 2,154
Message 59436 - Posted: 14 Jan 2019, 14:33:19 UTC - in response to Message 59431.  

but you cant compare your system with theis system ;)

i think they can use a big bandwith, at least 10 gbit i think


My system came with a PCIE two-channel 10 Gbit/sec NIC. I have unplugged it because I have nothing that fast to use it with. Its main chip has a big heat sink on it with a little fan to blow cooling air over the heat sink. Its other chip also has a big heat sink on it, but no fan.

My Internet connection will do 75 Megabit/sec if the server at the other end will do it; few do.
ID: 59436 · Report as offensive     Reply Quote
ProfileDave Jackson
Volunteer moderator

Send message
Joined: 15 May 09
Posts: 4541
Credit: 19,039,635
RAC: 18,944
Message 59437 - Posted: 14 Jan 2019, 14:50:33 UTC - in response to Message 59431.  

Two hadcm3s zips of 107MB just succeeded but restart needed two attempts. Out.zip also gone now. Expect transient upload errors until the servers stop getting hammered.
ID: 59437 · Report as offensive     Reply Quote
Jean-David Beyer

Send message
Joined: 5 Aug 04
Posts: 1120
Credit: 17,202,915
RAC: 2,154
Message 59438 - Posted: 14 Jan 2019, 15:17:57 UTC - in response to Message 59437.  

Two hadcm3s zips of 107MB just succeeded but restart needed two attempts. Out.zip also gone now.


Five hadcm3s zips of 107MB just succeeded and restart.zip needed two attempts. Out.zip also gone now.
ID: 59438 · Report as offensive     Reply Quote
Jean-David Beyer

Send message
Joined: 5 Aug 04
Posts: 1120
Credit: 17,202,915
RAC: 2,154
Message 59443 - Posted: 14 Jan 2019, 20:11:40 UTC - in response to Message 59438.  

It seems it even worked after all that.
But I did not get any more credit than one of the other users who died from an Error while computing message.

Name hadcm3s_x5300_190012_60_771_011668342_2
Workunit 11668342
Created 6 Jan 2019, 16:46:40 UTC
Sent 6 Jan 2019, 16:46:53 UTC
Report deadline 19 Dec 2019, 22:06:53 UTC
Received 14 Jan 2019, 20:06:36 UTC
Server state Over
Outcome Success
Client state Done
Exit status 0 (0x0)
Computer ID 1256552
Run time 5 days 1 hours 0 min 35 sec
CPU time 4 days 18 hours 26 min 5 sec
Validate state Initial
Credit 1,556.06
Device peak FLOPS 1.28 GFLOPS
Application version UK Met Office HadCM3 short v8.34
i686-pc-linux-gnu
stderr out

<core_client_version>7.2.33</core_client_version>
<![CDATA[
<stderr_txt>
Suspended CPDN Monitor - Suspend request from BOINC...
Suspended CPDN Monitor - Suspend request from BOINC...
Suspended CPDN Monitor - Suspend request from BOINC...
Suspended CPDN Monitor - Suspend request from BOINC...
Suspended CPDN Monitor - Suspend request from BOINC...
CPDN Monitor - Quit request from BOINC...
Processing restart Year 1905 Month 12 Day 1
Calling boinc_finish...10:54:28 (19103): called boinc_finish(0)
In boinc_exit called with status 0
Calloing set_signal_exit_code with status 0

</stderr_txt>
]]>
ID: 59443 · Report as offensive     Reply Quote
ProfileJIM

Send message
Joined: 31 Dec 07
Posts: 1152
Credit: 22,363,583
RAC: 5,022
Message 59446 - Posted: 15 Jan 2019, 2:27:27 UTC

Finally, after many failures and back offs my zip are slowly uploading. I know the server must be getting really hammered, what with 5 day of backlog to get through. If my relatively slow computers built up 33 zips in the time the fast 3.5GHz machine must have created a lot more.
ID: 59446 · Report as offensive     Reply Quote
ProfileDave Jackson
Volunteer moderator

Send message
Joined: 15 May 09
Posts: 4541
Credit: 19,039,635
RAC: 18,944
Message 59447 - Posted: 15 Jan 2019, 9:53:50 UTC - in response to Message 59446.  

the fast 3.5GHz machine must have created a lot more.

My slow laptop had over 2.5GB of files to upload. There are quite a few fast machines with 20+ cores out there crunching away. And I notice that the number of computers with recent credit is now up above 12,000. I suspect the next batch of work will fly of the shelves very quickly.
ID: 59447 · Report as offensive     Reply Quote
Previous · 1 · 2 · 3 · 4 · 5

Message boards : Number crunching : Upload server is out of disk space

©2024 cpdn.org